Test results
GA4 Tracking Plan Limits: test results
Tested 2026-10-19, skill version 1.0.0 at the time of loading this page. We run every skill on a strong and a weak model before it is listed, and publish both verdicts, including where the weak one fails.
Verdicts
- Date
- 2026-10-19
- Strong · claude-sonnet-5-5 (Claude Code alias "sonnet")
- Right on all 3 cases, read by hand. On the shop plan it named the event of 43 characters with the count and left out the parameter name of exactly 40. On the help-centre plan it gave the reserved event name and the order number held in a user-scoped dimension, and left out the event with exactly 25 parameters. On the clean billing plan, with an event name of exactly 40 characters, it answered exactly No findings.
- Weak · claude-haiku-5-5 (Claude Code alias "haiku")
- Right on all 3 cases, read by hand. It gave the same single line for the long event name, the two expected lines for the help-centre plan, and exactly No findings for the clean plan, including the 40-character event name. Its suggested shorter names were its own and were counted correctly.
Note
Light test: three cases (two planted, one clean), one run per model; no comparison without the skill. The three inputs were written by us; each planted one carries a safe look-alike and neither has a comment pointing at the defect. Facts come from the public pages named in the notes, read on 19 October 2026; there are no owner-measured facts.
What was not measured
- Models other than the two named above were not run.
- Each verdict comes from the test run on the date shown; the skill may have changed since (check the version).
- Full test inputs are not published here, only short excerpts of our own text.
- Results on your own texts, languages and domains can differ.